You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Starting on #6296, we began instantiating the model on the accelerator passed on the command line. Then, for XLA executions, we moved the model to the XLA device. While it worked for most of the models, it also broke a few others:
detectron2_fasterrcnn_r_101_c4
detectron2_fasterrcnn_r_101_dc5
detectron2_fasterrcnn_r_101_fpn
detectron2_fasterrcnn_r_50_c4
detectron2_fasterrcnn_r_50_dc5
detectron2_fasterrcnn_r_50_fpn
detectron2_fcos_r_50_fpn
detectron2_maskrcnn_r_101_c4
detectron2_maskrcnn_r_101_fpn
detectron2_maskrcnn_r_50_c4
detectron2_maskrcnn_r_50_fpn
hf_Bart
timm_regnet
mobilenet_v3_large
These are breaking on both non-dynamo and dynamo+openxla.
ysiraichi
changed the title
Torchbench regression changing load_benchmark method.
[torchbench] Regression after changing load_benchmark method.
Jan 22, 2024
🐛 Bug
Starting on #6296, we began instantiating the model on the accelerator passed on the command line. Then, for XLA executions, we moved the model to the XLA device. While it worked for most of the models, it also broke a few others:
These are breaking on both non-dynamo and dynamo+openxla.
Raw Error
To Reproduce
Environment
Additional Context
Further discussion can be found on #6336
cc @miladm @JackCaoG
The text was updated successfully, but these errors were encountered: